Introducing the VoicePrivacy Initiative

Tomashenko, Natalia; Srivastava, Brij Mohan Lal; Wang, Xin; Vincent, Emmanuel; Nautsch, Andreas; Yamagishi, Junichi; Evans, Nicholas; Patino, José; Bonastre, Jean-François; Noé, Paul-Gauthier; Todisco, Massimiliano

doi:10.21437/interspeech.2020-1333

Cited by 76 publications

(130 citation statements)

References 33 publications

Supporting

Mentioning

130

Contrasting

Order By: Relevance

“…Most recently proposed solutions for privacy preservation fall between anonymization and cryptography [7]. Although these solutions were effective in anatomizing the speaker identity, they may prevent speaker authentication regarding voice assistive systems activation.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Configurable Privacy-Preserving Automatic Speech Recognition

Aloufi¹,

Haddadi²,

Boyle³

2021

Interspeech 2021

View full text Add to dashboard Cite

Voice assistive technologies have given rise to far-reaching privacy and security concerns. In this paper we investigate whether modular automatic speech recognition (ASR) can improve privacy in voice assistive systems by combining independently trained separation, recognition, and discretization modules to design configurable privacy-preserving ASR systems. We evaluate privacy concerns and the effects of applying various stateof-the-art techniques at each stage of the system, and report results using task-specific metrics (i.e. WER, ABX, and accuracy). We show that overlapping speech inputs to ASR systems present further privacy concerns, and how these may be mitigated using speech separation and optimization techniques. Our discretization module is shown to minimize paralinguistics privacy leakage from ASR acoustic models to levels commensurate with random guessing. We show that voice privacy can be configurable, and argue this presents new opportunities for privacy-preserving applications incorporating ASR.

show abstract

Section: Discussionmentioning

confidence: 99%

“…The recent VoicePrivacy initiative [7] promotes the development of anonymization methods that aim to suppress personally identifiable information in speech (i.e. speaker identity) while leaving linguistic content intact.…”

Section: Privacy-preserving Voice Analyticsmentioning

confidence: 99%

Configurable Privacy-Preserving Automatic Speech Recognition

Aloufi¹,

Haddadi²,

Boyle³

2021

Interspeech 2021

View full text Add to dashboard Cite

show abstract

“…Finally, the primary baseline of the VoicePrivacy Challenge 2020 (VPC) [25] uses a neural synthesizer [9,26] to synthesize speech given the target x-vector and fundamental frequency and bottleneck features extracted from the source.…”

Section: Anonymization Techniques and Target Selectionmentioning

confidence: 99%

“…In the legal community, the term "anonymization" means that this goal has been achieved. Following the VoicePrivacy Challenge[25], we use it to refer to the task, even when the technique has failed.…”

mentioning

confidence: 99%

A Comparative Study of Speech Anonymization Metrics

Maouche¹,

Srivastava²,

Vauquier³

et al. 2020

Interspeech 2020

Self Cite

View full text Add to dashboard Cite

Speech anonymization techniques have recently been proposedfor preserving speakers' privacy. They aim at concealing speakers' identities while preserving the spoken content. In this study, we compare three metrics proposed in the literature to assess the level of privacy achieved. We exhibit through simulation the differences and blindspots of some metrics. In addition, we conduct experiments on real data and state-of-the-art anonymization techniques to study how they behave in a practical scenario. We show that the application-independent log-likelihood-ratio cost function C min llr provides a more robust evaluation of privacy than the equal error rate (EER), and that detection-based metrics provide different information from linkability metrics. Interestingly, the results on real data indicate that current anonymization design choices do not induce a regime where the differences between those metrics become apparent.

show abstract

“…In recent years, there has been a growing interest in privacy preservation solutions for speech technology. To promote the development of privacy preservation techniques for speech, the VoicePrivacy initiative has recently been introduced in [3], which focused on the voice anonymisation task.…”

Section: Introductionmentioning

confidence: 99%

Anonymous Speaker Clusters: Making Distinctions Between Anonymised Speech Recordings with Clustering Interface

O’Brien¹,

Tomashenko²,

Chanclu³

et al. 2021

Interspeech 2021

Self Cite

View full text Add to dashboard Cite

Our study examined the performance of evaluators tasked to group natural and anonymised speech recordings into clusters based on their perceived similarities. Speech stimuli were selected from the VCTK corpus; two systems developed for the VoicePrivacy 2020 Challenge were used for anonymisation. The Baseline-1 (B1) system was developed by using x-vectors and neural waveform models, while the Baseline-2 (B2) system relied on digital-signal-processing techniques. 74 evaluators completed three trials composed of 16 recordings with either natural or anonymised speech generated from a single system. F-measure and cluster purity metrics were used to assess evaluator accuracy. Probabilistic linear discriminant analysis (PLDA) scores from an automatic speaker verification system were generated to quantify similarity between recordings and used to correlate subjective results. Our findings showed that non-native English speaking evaluators significantly lowered their F-measure means when presented anonymised recordings. We observed no significance for cluster purity. Pearson correlation procedures revealed that PLDA scores generated from natural and B2-anonymised speech recordings correlated positively to F-measure and cluster purity metrics. These findings show evaluators were able to use the interface to cluster natural and anonymised speech recordings and suggest anonymisation systems modelled like B1 are more effective at suppressing identifiable speech characteristics.

show abstract

Introducing the VoicePrivacy Initiative

Cited by 76 publications

References 33 publications

Configurable Privacy-Preserving Automatic Speech Recognition

Configurable Privacy-Preserving Automatic Speech Recognition

A Comparative Study of Speech Anonymization Metrics

Anonymous Speaker Clusters: Making Distinctions Between Anonymised Speech Recordings with Clustering Interface

Contact Info

Product

Resources

About